Analysis of Risk Factors and Development of a Risk Prediction Model for Venous Thrombosis in Patients with Viral Pneumonia

This study aimed to identify independent risk factors for venous thromboembolism (VTE) in patients with viral pneumonia, including those with COVID-19, and to develop a predictive model using clinical data from 1,124 patients (95 VTE cases and 1,029 non-VTE cases) sourced from the MIMIC-IV database. Through LASSO and multivariate logistic regression analyses, key predictors identified were race, mechanical ventilation, length of hospital stay (LOS_hospital), activated partial thromboplastin time (APTT), anion gap, mean corpuscular volume (MCV), platelet, and white blood cell count (WBC). A nomogram prediction model incorporating these variables demonstrated robust predictive performance, achieving an area under the ROC curve (AUC) of 0.803 (95% CI: 0.761–0.845). Calibration curves confirmed high consistency between predicted and observed risks, while decision curve analysis validated the model’s clinical utility for individualized risk assessment and management. This tool enables rapid, precise VTE risk assessment in viral pneumonia patients, supporting targeted thromboprophylaxis and informed clinical decision-making to improve outcomes.